- Tutorial on Synthetic Data in the Era of LLMs at ACL 2025
- Published Tülu 3 paper
- OLMo won the Best Theme Paper Award at ACL 2024
- Tulu 2.5 accepted to NeurIPS 2024
- Multiple papers accepted by ACL 2023, ICLR 2024, etc.
- Released Natural Instructions V2, covering 1600+ NLP tasks and their instructions
Research Experience
- Research Scientist at ByteDance Seed
- Incoming Assistant Professor at the CS Department, University of Texas at Austin
- Research projects include instruction tuning, synthetic data generation, RLVR, and open language models
Education
PhD: Paul G. Allen School of Computer Science & Engineering at the University of Washington, co-advised by Hannaneh Hajishirzi and Noah Smith.
Background
Research Interests: How (natural/human) language can help AI understand, reason, learn, communicate, and interact with the world. Professional Field: Computer Science, particularly in Natural Language Processing.